Empirical study of hybrid particle swarm optimizers with the simplex method operator

Abstract

A novel hybrid simplex method and particle swarm optimization (HSMPSO) algorithm is presented in this article. Computational experiments on variety of benchmark functions indicate this SM-PSO hybrid is a promising way for locating global optima of continuous multimodal functions. Although very easy to be implemented, the hybrid method yields competitive results in both reliability and efficiency compared to other published algorithms. We provide an extensive analysis of the impact of the parameters of our hybrid algorithm on its performance as well.